English
Related papers

Related papers: Gram: Assessing sabotage propensities via automate…

200 papers

Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not…

Machine Learning · Computer Science 2026-04-27 Meghana Karnam , Ananya Joshi

Sufficiently capable models could subvert human oversight and decision-making in important contexts. For example, in the context of AI development, models could covertly sabotage efforts to evaluate their own dangerous capabilities, to…

The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats…

Machine Learning · Computer Science 2025-04-22 Song Xia , Wenhan Yang , Yi Yu , Xun Lin , Henghui Ding , Ling-Yu Duan , Xudong Jiang

This paper investigates the following problem: how to find a GSMem malicious activity effectively. To this end, this paper puts forward a new method based on Artificial Intelligence (AI). At first, we use a large quantity of data in terms…

Cryptography and Security · Computer Science 2018-01-17 WeiJun Zhu , ShaoHuan Ban , YongWen Fan

This memorandum presents four recommendations aimed at strengthening the principles of AI model reliability and AI model governability, as DoW, ODNI, NIST, and CAISI refine AI assurance frameworks under the AI Action Plan. Our focus…

Computers and Society · Computer Science 2025-10-13 Matteo Pistillo , Charlotte Stix

Fraud can pose a challenge in many resource allocation domains, including social service delivery and credit provision. For example, agents may misreport private information in order to gain benefits or access to credit. To mitigate this, a…

Computer Science and Game Theory · Computer Science 2026-04-29 Sanmay Das , Fang-Yi Yu , Yuang Zhang

If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed…

Artificial Intelligence · Computer Science 2025-05-26 Marie Davidsen Buhl , Jacob Pfau , Benjamin Hilton , Geoffrey Irving

Rising concern for the societal implications of artificial intelligence systems has inspired a wave of academic and journalistic literature in which deployed systems are audited for harm by investigators from outside the organizations…

The emerging paradigm of AI co-scientists focuses on tasks characterized by repeatable verification, where agents explore search spaces in 'guess and check' loops. This paradigm does not extend to problems where repeated evaluation is…

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

Artificial Intelligence · Computer Science 2025-05-20 Lili Zhang , Haomiaomiao Wang , Long Cheng , Libao Deng , Tomas Ward

Creating systems that are aligned with our goals is seen as a leading approach to create safe and beneficial AI in both leading AI companies and the academic field of AI safety. We defend the view that misaligned AGI - future, generally…

Computers and Society · Computer Science 2025-06-05 Max Hellrigel-Holderbaum , Leonard Dung

We study the multi-armed bandit (MAB) problem where the agent receives a vectorial feedback that encodes many possibly competing objectives to be optimized. The goal of the agent is to find a policy, which can optimize these objectives…

Machine Learning · Computer Science 2017-06-16 Robert Busa-Fekete , Balazs Szorenyi , Paul Weng , Shie Mannor

With the steady rise of the use of AI in bio-technical applications and the widespread adoption of genomics sequencing, an increasing amount of AI-based algorithms and tools is entering the research and production stage affecting critical…

Machine Learning · Computer Science 2024-01-22 Heorhii Skovorodnikov , Hoda Alkhzaimi

Safety-critical scenarios are essential for training and evaluating autonomous driving (AD) systems, yet remain extremely rare in real-world driving datasets. To address this, we propose Real-world Crash Grounding (RCG), a scenario…

Robotics · Computer Science 2025-07-16 Benjamin Stoler , Juliet Yang , Jonathan Francis , Jean Oh

We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--such as sycophantic deference, opposition to AI regulation,…

Computation and Language · Computer Science 2026-03-11 Abhay Sheshadri , Aidan Ewart , Kai Fronsdal , Isha Gupta , Samuel R. Bowman , Sara Price , Samuel Marks , Rowan Wang

Agents operating with computer and Web use inevitably encounter errors: inaccessible webpages, missing files, local and remote misconfigurations, etc. These errors do not thwart agents based on state-of-the-art models. They helpfully…

Computation and Language · Computer Science 2026-05-20 Rishi Jha , Harold Triedman , Arkaprabha Bhattacharya , Vitaly Shmatikov

AI methods have been proven to yield impressive performance on Android malware detection. However, most AI-based methods make predictions of suspicious samples in a black-box manner without transparency on models' inference. The expectation…

Cryptography and Security · Computer Science 2022-11-21 Zhi Lu , Vrizlynn L. L. Thing

The rapid integration of Artificial Intelligence (AI)-based systems offers benefits for various domains of the economy and society but simultaneously raises concerns due to emerging scandals. These scandals have led to the increasing…

Computers and Society · Computer Science 2024-11-28 L. H. Nguyen , S. Lins , G. Du , A. Sunyaev

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…

Computers and Society · Computer Science 2026-02-24 Nelu D. Radpour

The transition to smart grids has increased the vulnerability of electrical power systems to advanced cyber threats. To safeguard these systems, comprehensive security measures-including preventive, detective, and reactive strategies-are…

Cryptography and Security · Computer Science 2024-12-06 Omer Sen , Christoph Pohl , Immanuel Hacker , Markus Stroot , Andreas Ulbig